Hi all, My executions of DiffEqFlux.sciml_train are not optimizing but yet are iterating for the full amount without error. By not optimizing, I mean that for whatever random initial parameters I feed for a fitting example, the loss function does not change at each iteration and the final minimizer…

sciML_train func running but not optimizing

ChrisRackauckas April 14, 2021, 8:04pm 6

The reason is because this is incorrect during differentiation: you aren’t using Float64 values all of the time. Instead you’re looking for A = Array{eltype(u),2}(undef,3,3).

2 Likes

Topic		Replies	Views
From Scmil_train to Optimization.jl General Usage	26	723	February 13, 2023
Creating a loss function for sciml_train with unequal time point distribution of the ODE components General Usage question , diffeqflux	13	763	February 28, 2022
Problem with Zygote gradient Numerics zygote , differentialequation	10	897	December 16, 2021
Neural ODE fitting really slow Machine Learning diffeq , flux , sciml	13	2017	September 11, 2020
Unable to compute gradient of loss of my model with sciml_train General Usage question , sciml	5	763	January 28, 2021

sciML_train func running but not optimizing

Related topics